arXiv · cs.AI · Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya, Haruto Suzuki, Kuniaki Saito, Toshihiko Fukushima, Cristian C. Beltran-Hernandez, Mai Nishimura · 4 小时前模型评分45
CLAP：无需改动架构，直接把 视觉语言模型（VLM，Vision-Language Model） 适配成 VLA
CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding
导读
CLAP（Causal Language-Action Prediction，因果语言-动作预测）通过在数字动作序列前加上自然语言动作描述，把预训练视觉语言模型（VLM，Vision-Language Model）直接转成视觉-语言-动作模型（VLA），无需改动主干架构。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：embodied-ai，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “To address this, we propose CLAP (Causal Language-Action Prediction), which prepends each numeric action sequence with a natural-language action description, causally conditioning precise action-token prediction on a language-action plan without modifying the backbone architecture.”
- “With only 4-5 hours of training, 2B CLAP achieves 90.8% on LIBERO (+14.9 pt over VLA-0) and improves robustness on LIBERO-PRO under language, object, and spatial perturbations.”
- “We release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage, enabling controlled analysis of VLM-to-VLA capability transfer.”
来源：arXiv · cs.AI · arxiv.org